Computer Engineering Commons^™

An Empirical Analysis Of New Perspectives For Strategy Solving In Intelligent Game-Theoretic Decision-Making, Jiongming Su, Junren Luo, Shaofei Chen

Journal of System Simulation

Abstract: With the development of artificial intelligence technology, especially the promotion of largescale pre-training model theory, some new perspectives of strategy solving for intelligent game-theoretic decision-making have gradually been widely concerned and discussed. This paper combines the development of artificial intelligence technology and the transformation of strategy solving paradigm for intelligent game-theoretic decision-making, takes Chess (two-player zero-sum perfect information game), diplomacy (multi-player general-sum imperfect information game), and StarCraft Multi-Agent Challenge (multi-agent Markov game) as the research object for empirical analysis on sequential decision-making, the new paradigm and new way of strategy solving are analyzed according to the new perspective of …

Point Cloud Registration Method Based On Improved Grey Wolf Algorithm And Adaptive Splitting Kd-Tree, Yuanhao Du, Xiuli Geng, Chengzhi Xu, Yinhua Liu

Journal of System Simulation

Abstract: Traditional GWO algorithms suffer from limitations such as insufficient search efficiency and susceptibility to local optima. A novel method for the registration of point clouds of complex industrial components is proposed based on an improved GWO algorithm and ICP. To address the problem of uneven population distribution caused by random initialization in GWO, chaotic mapping is employed to initialize the gray wolf population, ensuring a more uniform distribution of individuals within the search space. A non-linear control parameter strategy is introduced to strike a balance between the algorithm's local search and global search capabilities. Elite reverse learning is integrated …

Gaussian Chaotic Fire Hawk Optimization Algorithm For Solving Dynamic Optimization Problems, Yongzhang Chen, Yuanbin Mo

Journal of System Simulation

Abstract: There are many important chemical processes in the chemical industry rely on dynamic optimization with factors such as nonlinearity and discontinuity. In order to find a more efficient solution algorithm, Gaussian Chaotic fire hawk optimization algorithm is proposed based on the fire hawk optimization algorithm, which is used to solve such problems after parameterizing the control variables. The original way of initializing the populations is replaced using tent chaotic mapping in order to make more sense of the initial distribution of the algorithm; a more targeted update method has been proposed in the analysis of fire hawk location updates …

Retracted: Deep Learning-Based Beamforming Optimization For Reconfigurable Intelligent Surface-Assisted Wireless Communication Systems, Mohammed Firas Jassim, Alhamzah Taher Mohammed, Osamah Abdullah

Iraqi Journal for Computer Science and Mathematics

This research investigates how deep learning might be used to optimize beamforming in wireless communication systems that are helped by Reconfigurable Intelligent Surfaces (RIS). Our goal is to increase the possible data rates by dynamically forecasting the best phase shifts for RIS elements by utilizing Convolutional Neural Networks (CNN) and hybrid CNN-Long Short-Term Memory (CNN-LSTM) models. We assess the performance of these deep learning models against conventional genie-aided techniques by simulating real-world wireless settings using the DeepMIMO dataset. The findings demonstrate that beamforming based on deep learning can reach near-optimal performance, greatly lowering the overhead associated with channel estimation while …

The Permutation Annihilator Ideals In Commutative Permutation Bck–Algebras With Their Applications, Shuker Khalil, Ali Abbas Asmae

Iraqi Journal for Computer Science and Mathematics

This paper introduces new concepts such as permutation BCK--algebra, permutation involutory ideal, commutative permutation BCK--algebra, and prime permutation ideal. Additionally, their attributes are examined. This paper elucidates a method for determining a relationship between the chemical structure of atoms for the chemical element Cadmium, and some of our suggestions are given here. In this work, the structure of the sets 𝒜 and λ_n^β∗𝒜 are defined. Next, we show that if 𝒜 is a permutation ideal, then λ_n^β∗𝒜 is a permutation ideal that contains 𝒜. Also, in any commutative permutation BCK--algebra the …

Integrating Fuzzy Set Theory With Association Rule Mining For Advanced E-Commerce Recommendations, Hind Raad Ibraheem, Murtadha Mohammed Hamad

Iraqi Journal for Computer Science and Mathematics

The dynamic nature of e-commerce necessitates the adoption of cutting-edge technologies to improve the online shopping experience. Our research introduces a groundbreaking methodology called Fuzzy Association Rule Mining (FARM), combining fuzzy set theory with traditional Association Rule Mining (ARM). Unlike conventional ARM, which focuses solely on the frequency of jointly purchased items, FARM also considers the sold quantities, leveraging the Apriori algorithm to discern customer preferences from historical sales data across the UCI Online Retail II, Market Basket, and Movielens datasets. This hybrid of fuzzy set theory with ARM enables a better understanding of complicated consumer behaviors and associations between …

Liu-Type Estimator In Inverse Gaussian Regression Model Based On (R-(K-D)) Class Estimator, Zeina Ameer Hadied, Oday Esam Al-Saqal, Zakariya Yahya Algamal

Iraqi Journal for Computer Science and Mathematics

When multicollinearity arises in the inverse Gaussian regression (IGR), there is a substantially unstable variance in the maximum likelihood estimator. Based on the (r-(k-d)) class estimation method, we present a novel Liu-type estimator in the IGR model in this study. The study examines the e ectiveness of the suggested estimator and draws comparisons with alternative estimators. Based on simulation and real data results, the suggested estimate performs better than the other estimators in terms of mean squared error.

The Efficacy Of Utilizing Artificial Intelligence Techniques In Developing Critical Thinking In Mathematics Among Secondary School Students And Their Attitudes Toward It, Mohammad A. Tashtoush, Aida B. Qasimi, Nawal H. Shirawia, Lubna A. Hussein

Iraqi Journal for Computer Science and Mathematics

The aim of this study is to investigate the efficacy of Artificial Intelligence (AI) techniques and programs in developing Critical Thinking Skills (CTSs) in mathematics among secondary school students, as well as their attitudes towards it. This study employed an experimental methodology, which was applied to a sample of 91 students. A critical thinking test and a scale to measure students' Attitudes Towards Mathematics (ATM) were also utilized. This study revealed significant improvements in the mean scores of critical thinking skills among secondary students who were exposed to Artificial Intelligence Techniques (AITs), particularly in deduction, interpretation, inference, and evaluation. Additionally, …

Integrating Neural Networks For Predictive Torque Control And Obstacle Avoidance In Autonomous Robot, Viswanath Kodali, Harsha Vardhan Borra, Kiran P

Northeast Journal of Complex Systems (NEJCS)

In the field of robotics, precise motion control and accurate computation of joint forces are critical for ensuring optimal performance. Traditional methods, such as using the Jacobian matrix for joint angle determination and Euler-Lagrange equations for torque computation, are reliable but computationally intensive, making them less suitable for real-time applications. This paper presents an advanced approach to improving the productivity and efficiency of a 3-Degree of Freedom (DOF) robotic arm by utilizing Artificial Neural Network (ANN). The proposed system dynamically predicts joint angles and torque, enabling faster and more efficient motion control.

To address the challenge of obstacle avoidance in …

Email Spam Classification Based On Deep Learning Methods: A Review, Ekramul Haque Tusher, Mohd Arfian Ismail, Anis Farihan Mat Raffei

Iraqi Journal for Computer Science and Mathematics

Email spam is a significant issue confronting both email consumers and providers. The evolution of spam filtering has progressed considerably, transitioning from basic rule-based filters to more sophisticated machine learning algorithms. Deep learning has become a potent collection of techniques for addressing intricate issues such as spam classification in recent times. A thorough literature evaluation is required to have a comprehensive overview of the current research on utilizing deep learning methods for email spam classification. This review aims to identify the various deep learning techniques used for email spam, their effectiveness, and areas for future research. By synthesizing the outcomes …

Machine Learning And Shap Interpretability For Chronic Disease Understanding, Nnaemeka Charles Igwe, Khandaker Mamun Ahmed

SDSU Data Science Symposium

Non-communicable diseases (NCDs), such as diabetes, are major global health concerns influenced by various health parameters and lifestyle choices. Traditional methods struggle to efficiently predict and manage these conditions due to the complexity and diversity of medical data. There is a need to leverage machine learning algorithms and modern computational tools to accurately predict diabetes, improve diagnosis, and provide actionable insights for better healthcare outcomes. In this project we study the application of machine learning methods for predicting NCDs such as diabetes. Moreover, we leverage hyperparameter tuning techniques for model development and SHapley Additive exPlanation (SHAP) for results interpretations and …

Generative Ai For Synthetic Data Creation: Building Mastery-Focused Educational Datasets, Tapiwa Amion Chinodakufa, Khandaker Mamun Ahmed

SDSU Data Science Symposium

Synthetic data is artificially generated data that mimics the statistical properties of real world data without exposing sensitive information. It is used in analysis, research, and deployments. Educational technology (EdTech) is an area where synthetic data can solve the problems of data scarcity, privacy concerns, regulatory compliance, bias reduction, data quality, data integrity, and cost efficiency. Our research aims to generate synthetic educational dataset by leveraging generative AI techniques such as Autoencoder, variational autoencoder and Copula-GAN. Our experimental results shows the significant progress in generating educational dataset and represents the data distribution of synthetic and real data.

Internet Of Things Devices Users’ Privacy Adherence: A Case Of Digital Ignorance, Akrasia Or Exhaustion?, Philip Bazanye, Walter F. Uys, Wallace Chigona

The African Journal of Information Systems

Internet of Things devices, such as those used in home automation, commercial and retail business, and smart cities, are vulnerable to attacks that affect all aspects of daily life. The upsurge in the use of IoT devices has increased the likelihood of cyber-attacks on end users. This research investigates the factors that influence IoT device users to adhere to privacy standards. This interpretivist exploratory research was guided by a three-phased approach. The interview questions were derived from the conceptual model and the constructs of Activity Theory, and themes were analyzed using deductive thematic analysis. The findings were elaborated with reference …

Retracted: A Review Of Breast Cancer Histological Image Classification: Challenges And Limitations, Israa Faisal Jassam, Abdulrahman Abbas Mukhlif, Ahmed Adil Nafea, Mustafa Adnan Tharthar, Ahmed Isam Khudhair

Iraqi Journal for Computer Science and Mathematics

This paper comprehensively reviews the classification of breast cancer histological images. The paper discusses the research objectives, methodologies used, and conclusions drawn, as well as suggestions for the future. The study is based on the ICIAR 2018 database, which is considered one of the largest databases available to support this research. The paper also addresses major challenges such as lack of data, variation in tissue preparation, class imbalance, and computational requirements. Advanced techniques such as deep learning (DL), transfer learning and data augmentation are explored, along with innovative models such as convolutional neural networks (CNNs) and generative adversarial networks (GANs). …

Generating Real-Time Synthetic Datasets To Improve Aerial Object Detection, Garrett Williams

Theses and Dissertations

The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance …

A Review On Exploring Artificial Intelligence Applications, Advancements, Issues, And Future Challenges, Sajid Naeem, Novman Nabeel, Waseem Beg, Shujaat Ali, Rajiv N. Kanojiya, Satish S. Mandawade, Chetan R. Yewale, Sc Kulkarni, Vt Salunke, Av Patil

Polytechnic Journal

Artificial intelligence (AI) is a transformative technology with diverse applications that is transforming several industries. AI is the use of systems and technology to replicate human intelligence and solve common real-world issues. Machine learning (ML) and deep learning are AI technologies that use algorithms to more accurately predict occurrences without the need for human intervention. Explainable Artificial Intelligence (XAI) refers to AI that can explain decisions or forecasts to human users. XAI seeks to improve AI systems' transparency, trustworthiness, and accountability, particularly when utilized in high-risk applications such as healthcare, finance, or security. This review article provides a thorough overview …

Mixed Ion-Electron Conducting Lixag Alloy Anode Enabling Stable Li Plating/Stripping In Solid-State Batteries Via Enhanced Li Diffusion Kinetic, Anran Cheng, Pei Gao, Ruxing Wang, Kangli Wang, Kai Jiang

EKU Faculty and Staff Scholarship

Although showing huge potential in prospering the marketplace of all-solid-state lithium metal batteries (ASSLMBs), garnet-type solid electrolytes (Li6.5La3Zr1.5Ta0.6O12, LLZTO) are critically plagued by interface instability with Li anode and the vulnerability to Li dendrite, which are attributed to poor Li diffusion kinetic in bulk Li metal. Herein, a LixAg solid solution alloy with high Li diffusion kinetic is reported as a mixed ion- electron conductor (MIEC) alloy anode. The high Li diffusion kinetic stemming from a low eutectic point and a high mutual solubility of LixAg could reduce the Li concentration gradient in the anode, regulate Li electrochemical potential, and …

Correlations Between Song Popularity And Their Audio Features Using Machine Learning, Rong Chen

Dissertations, Theses, and Capstone Projects

This project is an interactive visual project that explores the relationship between audio features and song popularity on Spotify using machine learning techniques. Through the collection of nearly half a million songs and implementation of seven different machine learning models, including Linear Regression, Random Forest, Decision Trees, and Gradient Boosting, I investigated how audio characteristics correlate with a song's popularity ranking. The project utilized MongoDB for data storage, Spotipy for API integration, and Streamlit with Plotly for visualization. This work provides insights into the practical challenges of large-scale music analysis and the relationship between technical audio characteristics and commercial success, …

Design And Implementation Of Uvm-Based Verification Framework For Deep Learning Accelerators, Randa Ahmed Hussein Aboudeif

Theses and Dissertations

Recent advancements in deep learning (DL) have made hardware accelerators, known as deep learning accelerators (DLAs), a preferred solution for numerous high-performance computing (HPC) applications, including speech recognition, computer vision, and image classification. DLAs are composed of hundreds of parallel processing engines to speed up computations and can gain access to pre-trained networks from the cloud or through on-chip memory to implement the DNN inference process. DLA verification is becoming an important and challenging phase. The verification process is required to handle the complex DLA design. Moreover, the reliability of DLAs is critical for assessment as they are involved in …

Navigating The Future Advancing Autonomous Vehicles Through Robust Target Recognition And Real-Time Avoidance, Mohammed Ahmed Mohammed Hussein

Theses and Dissertations

The problem being tackled by this thesis is a very important one and very relevant to our days and times: it is about making improved target recognition and enhanced real-time response skills in AVs under simulated conditions. Our plan is to put some enhanced sensory capabilities into these vehicles and see if that makes them safer and more reliable. We are using as our base a particular object recognition algorithm (YOLOv7) and a particular simulation environment (CARLA). We utilized the CARLA 0.9.14 simulator on Ubuntu 20.04 as a more stable option than the initially used CARLA 0.9.15 on Ubuntu 22.04, …